Commit
•
bc29382
1
Parent(s):
1ca0329
Upload 13 files
Browse files- 1_Pooling/config.json +10 -0
- README.md +128 -3
- config.json +31 -0
- config_sentence_transformers.json +9 -0
- eval/mse_evaluation_talks-en-ru-dev.tsv.gz_results.csv +121 -0
- eval/translation_evaluation_talks-en-ru-dev.tsv.gz_results.csv +121 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
CHANGED
@@ -1,3 +1,128 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: sentence-transformers
|
3 |
+
pipeline_tag: sentence-similarity
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- feature-extraction
|
7 |
+
- sentence-similarity
|
8 |
+
- transformers
|
9 |
+
|
10 |
+
---
|
11 |
+
|
12 |
+
# {MODEL_NAME}
|
13 |
+
|
14 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
15 |
+
|
16 |
+
<!--- Describe your model here -->
|
17 |
+
|
18 |
+
## Usage (Sentence-Transformers)
|
19 |
+
|
20 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
21 |
+
|
22 |
+
```
|
23 |
+
pip install -U sentence-transformers
|
24 |
+
```
|
25 |
+
|
26 |
+
Then you can use the model like this:
|
27 |
+
|
28 |
+
```python
|
29 |
+
from sentence_transformers import SentenceTransformer
|
30 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
31 |
+
|
32 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
33 |
+
embeddings = model.encode(sentences)
|
34 |
+
print(embeddings)
|
35 |
+
```
|
36 |
+
|
37 |
+
|
38 |
+
|
39 |
+
## Usage (HuggingFace Transformers)
|
40 |
+
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
|
41 |
+
|
42 |
+
```python
|
43 |
+
from transformers import AutoTokenizer, AutoModel
|
44 |
+
import torch
|
45 |
+
|
46 |
+
|
47 |
+
#Mean Pooling - Take attention mask into account for correct averaging
|
48 |
+
def mean_pooling(model_output, attention_mask):
|
49 |
+
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
50 |
+
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
51 |
+
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
52 |
+
|
53 |
+
|
54 |
+
# Sentences we want sentence embeddings for
|
55 |
+
sentences = ['This is an example sentence', 'Each sentence is converted']
|
56 |
+
|
57 |
+
# Load model from HuggingFace Hub
|
58 |
+
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
|
59 |
+
model = AutoModel.from_pretrained('{MODEL_NAME}')
|
60 |
+
|
61 |
+
# Tokenize sentences
|
62 |
+
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
63 |
+
|
64 |
+
# Compute token embeddings
|
65 |
+
with torch.no_grad():
|
66 |
+
model_output = model(**encoded_input)
|
67 |
+
|
68 |
+
# Perform pooling. In this case, mean pooling.
|
69 |
+
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
70 |
+
|
71 |
+
print("Sentence embeddings:")
|
72 |
+
print(sentence_embeddings)
|
73 |
+
```
|
74 |
+
|
75 |
+
|
76 |
+
|
77 |
+
## Evaluation Results
|
78 |
+
|
79 |
+
<!--- Describe how your model was evaluated -->
|
80 |
+
|
81 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
82 |
+
|
83 |
+
|
84 |
+
## Training
|
85 |
+
The model was trained with the parameters:
|
86 |
+
|
87 |
+
**DataLoader**:
|
88 |
+
|
89 |
+
`torch.utils.data.dataloader.DataLoader` of length 573 with parameters:
|
90 |
+
```
|
91 |
+
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
92 |
+
```
|
93 |
+
|
94 |
+
**Loss**:
|
95 |
+
|
96 |
+
`sentence_transformers.losses.MSELoss.MSELoss`
|
97 |
+
|
98 |
+
Parameters of the fit()-Method:
|
99 |
+
```
|
100 |
+
{
|
101 |
+
"epochs": 20,
|
102 |
+
"evaluation_steps": 100,
|
103 |
+
"evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
|
104 |
+
"max_grad_norm": 1,
|
105 |
+
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
106 |
+
"optimizer_params": {
|
107 |
+
"eps": 1e-06,
|
108 |
+
"lr": 2e-05
|
109 |
+
},
|
110 |
+
"scheduler": "WarmupLinear",
|
111 |
+
"steps_per_epoch": null,
|
112 |
+
"warmup_steps": 10000,
|
113 |
+
"weight_decay": 0.01
|
114 |
+
}
|
115 |
+
```
|
116 |
+
|
117 |
+
|
118 |
+
## Full Model Architecture
|
119 |
+
```
|
120 |
+
SentenceTransformer(
|
121 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
122 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
123 |
+
)
|
124 |
+
```
|
125 |
+
|
126 |
+
## Citing & Authors
|
127 |
+
|
128 |
+
<!--- Describe where people can find more information -->
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.40.2",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 105879
|
31 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.7.0",
|
4 |
+
"transformers": "4.40.2",
|
5 |
+
"pytorch": "2.3.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
eval/mse_evaluation_talks-en-ru-dev.tsv.gz_results.csv
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,MSE
|
2 |
+
0,100,2.8928473591804504
|
3 |
+
0,200,2.5566164404153824
|
4 |
+
0,300,2.2533923387527466
|
5 |
+
0,400,2.1163906902074814
|
6 |
+
0,500,2.0060131326317787
|
7 |
+
0,-1,1.9447039812803268
|
8 |
+
1,100,1.8183402717113495
|
9 |
+
1,200,1.7153803259134293
|
10 |
+
1,300,1.6524117439985275
|
11 |
+
1,400,1.6069402918219566
|
12 |
+
1,500,1.557883806526661
|
13 |
+
1,-1,1.5349174849689007
|
14 |
+
2,100,1.5173410065472126
|
15 |
+
2,200,1.491781324148178
|
16 |
+
2,300,1.465703547000885
|
17 |
+
2,400,1.4556304551661015
|
18 |
+
2,500,1.4481942169368267
|
19 |
+
2,-1,1.426389440894127
|
20 |
+
3,100,1.39577966183424
|
21 |
+
3,200,1.397869735956192
|
22 |
+
3,300,1.3791386038064957
|
23 |
+
3,400,1.3692201115190983
|
24 |
+
3,500,1.3584598898887634
|
25 |
+
3,-1,1.3564773835241795
|
26 |
+
4,100,1.3375140726566315
|
27 |
+
4,200,1.350619550794363
|
28 |
+
4,300,1.3260378502309322
|
29 |
+
4,400,1.3261851854622364
|
30 |
+
4,500,1.3078000396490097
|
31 |
+
4,-1,1.3175654225051403
|
32 |
+
5,100,1.3159305788576603
|
33 |
+
5,200,1.312108337879181
|
34 |
+
5,300,1.3263111002743244
|
35 |
+
5,400,1.2919967994093895
|
36 |
+
5,500,1.294526644051075
|
37 |
+
5,-1,1.279385481029749
|
38 |
+
6,100,1.2747685424983501
|
39 |
+
6,200,1.2767380103468895
|
40 |
+
6,300,1.254996843636036
|
41 |
+
6,400,1.2535860762000084
|
42 |
+
6,500,1.2596610002219677
|
43 |
+
6,-1,1.2512801215052605
|
44 |
+
7,100,1.2597366236150265
|
45 |
+
7,200,1.2454991228878498
|
46 |
+
7,300,1.2466656975448132
|
47 |
+
7,400,1.246230211108923
|
48 |
+
7,500,1.2257634662091732
|
49 |
+
7,-1,1.232503354549408
|
50 |
+
8,100,1.2363849207758904
|
51 |
+
8,200,1.2266166508197784
|
52 |
+
8,300,1.2310810387134552
|
53 |
+
8,400,1.222414243966341
|
54 |
+
8,500,1.2164912186563015
|
55 |
+
8,-1,1.219892967492342
|
56 |
+
9,100,1.227688044309616
|
57 |
+
9,200,1.2137078680098057
|
58 |
+
9,300,1.2234610505402088
|
59 |
+
9,400,1.1979183182120323
|
60 |
+
9,500,1.2115975841879845
|
61 |
+
9,-1,1.2157601304352283
|
62 |
+
10,100,1.1952522210776806
|
63 |
+
10,200,1.206289790570736
|
64 |
+
10,300,1.2036706320941448
|
65 |
+
10,400,1.2108158320188522
|
66 |
+
10,500,1.2024701572954655
|
67 |
+
10,-1,1.2090140953660011
|
68 |
+
11,100,1.2182735837996006
|
69 |
+
11,200,1.2103605084121227
|
70 |
+
11,300,1.1928360909223557
|
71 |
+
11,400,1.177027728408575
|
72 |
+
11,500,1.1905891820788383
|
73 |
+
11,-1,1.1902272701263428
|
74 |
+
12,100,1.186790969222784
|
75 |
+
12,200,1.186472550034523
|
76 |
+
12,300,1.191321574151516
|
77 |
+
12,400,1.1821781285107136
|
78 |
+
12,500,1.188904233276844
|
79 |
+
12,-1,1.1863697320222855
|
80 |
+
13,100,1.1789905838668346
|
81 |
+
13,200,1.1883879080414772
|
82 |
+
13,300,1.1763601563870907
|
83 |
+
13,400,1.170448400080204
|
84 |
+
13,500,1.180951576679945
|
85 |
+
13,-1,1.1650272645056248
|
86 |
+
14,100,1.1710796505212784
|
87 |
+
14,200,1.2021472677588463
|
88 |
+
14,300,1.1722701601684093
|
89 |
+
14,400,1.1790373362600803
|
90 |
+
14,500,1.1628378182649612
|
91 |
+
14,-1,1.1735523119568825
|
92 |
+
15,100,1.1557640507817268
|
93 |
+
15,200,1.1770031414926052
|
94 |
+
15,300,1.1650467291474342
|
95 |
+
15,400,1.1652232147753239
|
96 |
+
15,500,1.170414499938488
|
97 |
+
15,-1,1.1694228276610374
|
98 |
+
16,100,1.1606036685407162
|
99 |
+
16,200,1.1659459210932255
|
100 |
+
16,300,1.1610891669988632
|
101 |
+
16,400,1.1743003502488136
|
102 |
+
16,500,1.1713393963873386
|
103 |
+
16,-1,1.1815223842859268
|
104 |
+
17,100,1.170582603663206
|
105 |
+
17,200,1.1600999161601067
|
106 |
+
17,300,1.1696469970047474
|
107 |
+
17,400,1.1701789684593678
|
108 |
+
17,500,1.1631796136498451
|
109 |
+
17,-1,1.1578342877328396
|
110 |
+
18,100,1.1727497912943363
|
111 |
+
18,200,1.1746379546821117
|
112 |
+
18,300,1.1589095927774906
|
113 |
+
18,400,1.1534282937645912
|
114 |
+
18,500,1.16147855296731
|
115 |
+
18,-1,1.1479795910418034
|
116 |
+
19,100,1.1532638221979141
|
117 |
+
19,200,1.1479231528937817
|
118 |
+
19,300,1.1513863690197468
|
119 |
+
19,400,1.148157473653555
|
120 |
+
19,500,1.1485524475574493
|
121 |
+
19,-1,1.1491804383695126
|
eval/translation_evaluation_talks-en-ru-dev.tsv.gz_results.csv
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,src2trg,trg2src
|
2 |
+
0,100,0.764,0.69
|
3 |
+
0,200,0.776,0.706
|
4 |
+
0,300,0.785,0.734
|
5 |
+
0,400,0.793,0.747
|
6 |
+
0,500,0.8,0.758
|
7 |
+
0,-1,0.808,0.763
|
8 |
+
1,100,0.807,0.777
|
9 |
+
1,200,0.81,0.787
|
10 |
+
1,300,0.813,0.793
|
11 |
+
1,400,0.824,0.796
|
12 |
+
1,500,0.828,0.796
|
13 |
+
1,-1,0.837,0.801
|
14 |
+
2,100,0.839,0.806
|
15 |
+
2,200,0.841,0.804
|
16 |
+
2,300,0.849,0.808
|
17 |
+
2,400,0.853,0.812
|
18 |
+
2,500,0.854,0.809
|
19 |
+
2,-1,0.858,0.81
|
20 |
+
3,100,0.865,0.817
|
21 |
+
3,200,0.875,0.816
|
22 |
+
3,300,0.877,0.82
|
23 |
+
3,400,0.877,0.82
|
24 |
+
3,500,0.882,0.824
|
25 |
+
3,-1,0.884,0.82
|
26 |
+
4,100,0.881,0.823
|
27 |
+
4,200,0.884,0.823
|
28 |
+
4,300,0.888,0.828
|
29 |
+
4,400,0.889,0.822
|
30 |
+
4,500,0.894,0.823
|
31 |
+
4,-1,0.888,0.812
|
32 |
+
5,100,0.89,0.819
|
33 |
+
5,200,0.889,0.82
|
34 |
+
5,300,0.891,0.82
|
35 |
+
5,400,0.887,0.826
|
36 |
+
5,500,0.891,0.823
|
37 |
+
5,-1,0.892,0.827
|
38 |
+
6,100,0.891,0.831
|
39 |
+
6,200,0.893,0.826
|
40 |
+
6,300,0.893,0.834
|
41 |
+
6,400,0.895,0.832
|
42 |
+
6,500,0.896,0.829
|
43 |
+
6,-1,0.894,0.837
|
44 |
+
7,100,0.897,0.836
|
45 |
+
7,200,0.897,0.832
|
46 |
+
7,300,0.9,0.829
|
47 |
+
7,400,0.896,0.831
|
48 |
+
7,500,0.902,0.838
|
49 |
+
7,-1,0.9,0.834
|
50 |
+
8,100,0.899,0.842
|
51 |
+
8,200,0.899,0.842
|
52 |
+
8,300,0.903,0.839
|
53 |
+
8,400,0.904,0.845
|
54 |
+
8,500,0.901,0.841
|
55 |
+
8,-1,0.898,0.846
|
56 |
+
9,100,0.901,0.851
|
57 |
+
9,200,0.901,0.851
|
58 |
+
9,300,0.9,0.85
|
59 |
+
9,400,0.904,0.855
|
60 |
+
9,500,0.906,0.854
|
61 |
+
9,-1,0.902,0.852
|
62 |
+
10,100,0.908,0.857
|
63 |
+
10,200,0.897,0.856
|
64 |
+
10,300,0.904,0.857
|
65 |
+
10,400,0.904,0.851
|
66 |
+
10,500,0.905,0.861
|
67 |
+
10,-1,0.901,0.856
|
68 |
+
11,100,0.906,0.856
|
69 |
+
11,200,0.903,0.862
|
70 |
+
11,300,0.911,0.864
|
71 |
+
11,400,0.904,0.867
|
72 |
+
11,500,0.907,0.867
|
73 |
+
11,-1,0.906,0.868
|
74 |
+
12,100,0.907,0.868
|
75 |
+
12,200,0.914,0.867
|
76 |
+
12,300,0.902,0.869
|
77 |
+
12,400,0.909,0.867
|
78 |
+
12,500,0.908,0.866
|
79 |
+
12,-1,0.905,0.861
|
80 |
+
13,100,0.907,0.871
|
81 |
+
13,200,0.913,0.875
|
82 |
+
13,300,0.909,0.875
|
83 |
+
13,400,0.913,0.873
|
84 |
+
13,500,0.909,0.871
|
85 |
+
13,-1,0.904,0.88
|
86 |
+
14,100,0.911,0.871
|
87 |
+
14,200,0.914,0.876
|
88 |
+
14,300,0.917,0.877
|
89 |
+
14,400,0.913,0.871
|
90 |
+
14,500,0.917,0.878
|
91 |
+
14,-1,0.914,0.879
|
92 |
+
15,100,0.917,0.887
|
93 |
+
15,200,0.91,0.885
|
94 |
+
15,300,0.908,0.882
|
95 |
+
15,400,0.915,0.886
|
96 |
+
15,500,0.914,0.883
|
97 |
+
15,-1,0.919,0.883
|
98 |
+
16,100,0.922,0.885
|
99 |
+
16,200,0.922,0.887
|
100 |
+
16,300,0.924,0.893
|
101 |
+
16,400,0.915,0.891
|
102 |
+
16,500,0.914,0.885
|
103 |
+
16,-1,0.915,0.887
|
104 |
+
17,100,0.916,0.889
|
105 |
+
17,200,0.918,0.888
|
106 |
+
17,300,0.921,0.882
|
107 |
+
17,400,0.921,0.89
|
108 |
+
17,500,0.915,0.887
|
109 |
+
17,-1,0.918,0.895
|
110 |
+
18,100,0.916,0.888
|
111 |
+
18,200,0.916,0.884
|
112 |
+
18,300,0.922,0.889
|
113 |
+
18,400,0.921,0.897
|
114 |
+
18,500,0.92,0.895
|
115 |
+
18,-1,0.921,0.892
|
116 |
+
19,100,0.921,0.895
|
117 |
+
19,200,0.923,0.897
|
118 |
+
19,300,0.921,0.897
|
119 |
+
19,400,0.921,0.895
|
120 |
+
19,500,0.922,0.895
|
121 |
+
19,-1,0.918,0.895
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cf601c0bb9ffa9ed108f3383d6aca9776929bf35b211a3919efd8704a6b21bf
|
3 |
+
size 669448040
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|